recenter on where we are, what's done/left, and where necessary reflect on our work's principle compliance, performance, and pristineness.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add majiayu000/claude-skill-registry --skill recenter-reflect --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Recenter Reflect?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-recenter-reflect)More formats (shields.io, HTML) on the badges page.
---
name: recenter-reflect
description: recenter on where we are, what's done/left, and where necessary reflect on our work's principle compliance, performance, and pristineness.
---
Let's take a step back and recenter the conversation. Provide an update based on your status. Catch the person up, provide context, lay out assumptions, state problems, and propose solutions with paths to get there. Now is an opportunity to speak our minds and remember our ultimate aims and principle instructions.
- What is done, what is left?
- What were the key assumptions of our implementation?
- What information did we consult?
- Where's unnecessary complexity?
- Blank slate, knowing what you know now, what would we do differently if starting over?
- What can be deleted (files, abstractions, options, config)?
- Are we aligned with repo conventions (SSOT, naming, structure)?Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
